There is no way to launder money anymore, because GCN will easily track down all dirty bitcoins.
New machine learning techniques have made it possible to detect criminal activity on the Bitcoin blockchain, including money laundering and transferring funds to suspicious wallets. This was reported by researchers from Elliptic in collaboration with the MIT-IBM Watson AI Lab.
The study analyzed a 26-GIGABYTE dataset containing 122,000 labeled subgraphs within a blockchain that includes 49 million nodes and 196 million transactions. The dataset was named "Elliptic2" by the researchers, and the information obtained made it possible to determine the links between wallets and transactions related to illegal activities in the blockchain.
It's not hard to guess that "Elliptic2" is a continuation of the "Elliptic1" study originally published in July 2019. The goal of the project is to fight financial crimes using machine learning technologies, namely graph convolutional neural networks (GCN).
Tom Robinson, chief scientific officer and co-founder of Elliptic, explained that using machine learning at the subgraph level allows you to predict whether certain cryptotransactions are proceeds of criminal activity. This differs from traditional methods of analysis aimed at tracking the activity of obviously illegal crypto wallets.
The study used three subgraph classification methods: GNN-Seg, Sub2Vec, and GLASS, which allowed us to identify many crypto exchange accounts that are potentially engaged in illegitimate activities.
Various patterns of cryptocurrency laundering were also identified, including the so-called "Peeling Chain". Further research will be aimed at improving the accuracy and detail of analysis methods, as well as expanding their application to other blockchains.
New machine learning techniques have made it possible to detect criminal activity on the Bitcoin blockchain, including money laundering and transferring funds to suspicious wallets. This was reported by researchers from Elliptic in collaboration with the MIT-IBM Watson AI Lab.
The study analyzed a 26-GIGABYTE dataset containing 122,000 labeled subgraphs within a blockchain that includes 49 million nodes and 196 million transactions. The dataset was named "Elliptic2" by the researchers, and the information obtained made it possible to determine the links between wallets and transactions related to illegal activities in the blockchain.
It's not hard to guess that "Elliptic2" is a continuation of the "Elliptic1" study originally published in July 2019. The goal of the project is to fight financial crimes using machine learning technologies, namely graph convolutional neural networks (GCN).
Tom Robinson, chief scientific officer and co-founder of Elliptic, explained that using machine learning at the subgraph level allows you to predict whether certain cryptotransactions are proceeds of criminal activity. This differs from traditional methods of analysis aimed at tracking the activity of obviously illegal crypto wallets.
The study used three subgraph classification methods: GNN-Seg, Sub2Vec, and GLASS, which allowed us to identify many crypto exchange accounts that are potentially engaged in illegitimate activities.
Various patterns of cryptocurrency laundering were also identified, including the so-called "Peeling Chain". Further research will be aimed at improving the accuracy and detail of analysis methods, as well as expanding their application to other blockchains.
